Goal: Write a one-page brief for one agent.

Prerequisites: Choose a business task and a person who can approve its boundaries.

Expected result: A brief covering purpose, audience, tone, guardrails, and handoff.

The 5 Planning Questions

Before you log into raia CX or upload a single document, you must define exactly what your agent is supposed to do. An AI agent without a clear purpose will behave erratically and provide poor customer experiences.

To build a successful agent, start by answering these five core questions:

Question 01: What is this agent FOR? (Its Primary Objective)

An AI agent's objective is its reason for being. It is the end state the agent is constantly striving to achieve. A vaguely defined goal leads to vague, unpredictable, and often useless behavior.

Instead of a generic goal like "Help customers," use a specific, actionable objective. A good objective defines the exact outcome the agent should reach before considering a conversation complete.

Examples of strong objectives:

• Resolve Tier 1 software login issues by guiding the user through password resets or clearing cache. If unresolved, create a support ticket.
• Qualify inbound sales leads by asking four specific BANT questions, then offer a link to book a demo.
• Answer employee questions about the HR handbook and PTO policies. Never answer questions about payroll.

Question 02: Who will it talk to? (The Target Audience)

Understanding your audience determines how the agent communicates. An agent serving enterprise IT administrators will use different language than one serving retail consumers. Consider:

• Technical proficiency level of your users
• Common frustrations or pain points they experience
• Whether they are internal employees or external customers
• The context in which they will interact (urgent support vs. casual browsing)

Question 03: What tone should it use? (Its Personality)

"Friendly" can mean many things. Instead, use descriptive pairs that give the agent a clear personality:

• Professional but warm, like a knowledgeable bank teller.
• Concise and highly technical, avoiding conversational filler.
• Empathetic and patient, acknowledging user frustration before offering solutions.

Tip: Always instruct the agent to be transparent about its identity. A good baseline rule is: ALWAYS state that you are an AI assistant if asked.

Question 04: What should it NEVER do? (Its Guardrails)

Guardrails are a system of rules and constraints that ensure an agent's behavior remains within acceptable, safe, and ethical boundaries. One of the most effective ways to implement guardrails is through negative constraints — explicitly telling the agent what not to do. Clear, direct prohibitions with strong commands can help, but test them, using commands like DO NOT or NEVER.

Category	Example Rule
Scope Boundaries	NEVER answer questions about competitor products.
Compliance	DO NOT provide medical, legal, or financial advice.
Security	NEVER ask the user to provide their full credit card number or password in the chat.
Hallucination Prevention	DO NOT guess. If the answer is not in your knowledge base, say you do not know and escalate to a human.

How many guardrails should you have? Start with 3 to 5 critical negative constraints. If you give an agent too many conflicting rules, it may become overly cautious and refuse to answer valid questions. Add more guardrails only when you observe specific behaviors you want to stop.

Question 05: When should it hand off to a human? (Its Escalation Rules)

No AI agent can handle 100% of interactions. A critical part of planning is deciding exactly when the agent should stop trying to help and instead bring a human into the loop via raia Copilot.

You should define clear triggers for escalation. These typically fall into three categories:

Trigger Type	When It Fires
Knowledge Gaps	The agent searches its vector store but cannot find a confident answer after two attempts.
Complexity	The user's issue requires account modifications, refunds, or system access the agent does not have.
Sentiment	The user expresses extreme frustration, uses profanity, or explicitly types "Talk to a human."

When an escalation is triggered, the agent will pause its automated responses and alert your team in Copilot, transferring the full context of the conversation so the human operator can pick up right where the AI left off.

FAQ: Can I change my agent's objective later? Yes. Your agent's instructions are fully editable in the raia CX Launch Pad. You can refine the objective, add new guardrails, or adjust the tone at any time based on real-world performance.

Practice check

Recommended practice: use a fictional support agent. Write one in-scope request and one request it should hand off; check both against your brief.